The Platforms Zoo
Deployment Paradigm Envelopes
The Platforms Zoo captures abstract deployment contexts — latency budgets, RAM envelopes, and storage tiers for Cloud, Edge, Mobile, and TinyML. These are teaching anchors, not chip specs. Pair them with Hardware entries for concrete silicon.
NoteReplaces
Systems.Tiers
Platform envelopes moved out of fleet topology into Platforms.* so Systems stays focused on nodes, fabrics, and clusters. See DATA_MODEL.md for the full layout.
| Platform | Latency Range | RAM Envelope | Typical Budget |
|---|---|---|---|
| Cloud | 100-500 | 100+ GiB | 200 ms |
| Edge | 10-100 | 30 GiB | 50 ms |
| Mobile | 5-50 | 8-16 | 30 ms |
| TinyML | 1-10 | 512 KiB | 100 ms |
Python Access
import mlsysim
cloud = mlsysim.Platforms.Cloud
edge = mlsysim.Platforms.Edge
mobile = mlsysim.Platforms.Mobile
tiny = mlsysim.Platforms.TinyUse platform envelopes when comparing deployment paradigms before committing to a specific accelerator from the Silicon Zoo.